FAL Image/Video MCP Server

Instructions

Implementation Reference

• src/index.ts:110-118 (registration)

  Registration of the 'luma_ray2' tool within the MODEL_REGISTRY.textToVideo array, defining its id, endpoint, name, and description.

  textToVideo: [
    { id: 'veo3', endpoint: 'fal-ai/veo3', name: 'Veo 3', description: 'Google DeepMind\'s latest with speech and audio' },
    { id: 'kling_master_text', endpoint: 'fal-ai/kling-video/v2.1/master/text-to-video', name: 'Kling 2.1 Master', description: 'Premium text-to-video with motion fluidity' },
    { id: 'pixverse_text', endpoint: 'fal-ai/pixverse/v4.5/text-to-video', name: 'Pixverse V4.5', description: 'Advanced text-to-video generation' },
    { id: 'magi', endpoint: 'fal-ai/magi', name: 'Magi', description: 'Creative video generation' },
    { id: 'luma_ray2', endpoint: 'fal-ai/luma-dream-machine/ray-2', name: 'Luma Ray 2', description: 'Latest Luma Dream Machine' },
    { id: 'wan_pro_text', endpoint: 'fal-ai/wan-pro/text-to-video', name: 'Wan Pro', description: 'Professional video effects' },
    { id: 'vidu_text', endpoint: 'fal-ai/vidu/q1/text-to-video', name: 'Vidu Q1', description: 'High-quality text-to-video' }
  ],

• src/index.ts:373-379 (schema)

  Dynamic input schema generation for text-to-video tools like 'luma_ray2' in generateToolSchema method.

  } else if (category === 'textToVideo') {
    baseSchema.inputSchema.properties = {
      prompt: { type: 'string', description: 'Text prompt for video generation' },
      duration: { type: 'number', default: 5, minimum: 1, maximum: 30 },
      aspect_ratio: { type: 'string', enum: ['16:9', '9:16', '1:1', '4:3', '3:4'], default: '16:9' },
    };
    baseSchema.inputSchema.required = ['prompt'];

• src/index.ts:627-675 (handler)

  The handleTextToVideo method provides the core execution logic for the 'luma_ray2' tool, calling the FAL API, processing the video output, handling downloads, and formatting the response.

  private async handleTextToVideo(args: any, model: any) {
    const { prompt, duration = 5, aspect_ratio = '16:9' } = args;
  
    try {
      // Configure FAL client lazily with query config override
      configureFalClient(this.currentQueryConfig);
      const inputParams: any = { prompt };
      
      if (duration) inputParams.duration = duration;
      if (aspect_ratio) inputParams.aspect_ratio = aspect_ratio;
  
      const result = await fal.subscribe(model.endpoint, { input: inputParams });
      const videoData = result.data as FalVideoResult;
      const videoProcessed = await downloadAndProcessVideo(videoData.video.url, model.id);
  
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify({
              model: model.name,
              id: model.id,
              endpoint: model.endpoint,
              prompt,
              video: {
                url: videoData.video.url,
                localPath: videoProcessed.localPath,
                ...(videoProcessed.dataUrl && { dataUrl: videoProcessed.dataUrl }),
                width: videoData.video.width,
                height: videoData.video.height,
              },
              metadata: inputParams,
              download_path: DOWNLOAD_PATH,
              data_url_settings: {
                enabled: ENABLE_DATA_URLS,
                max_size_mb: Math.round(MAX_DATA_URL_SIZE / 1024 / 1024),
              },
              autoopen_settings: {
                enabled: AUTOOPEN,
                note: AUTOOPEN ? "Files automatically opened with default application" : "Auto-open disabled"
              },
            }, null, 2),
          },
        ],
      };
    } catch (error) {
      throw new Error(`${model.name} generation failed: ${error}`);
    }
  }

• src/index.ts:476-482 (registration)

  Dispatch logic in the CallToolRequestSchema handler that identifies 'luma_ray2' as a textToVideo model and routes to the appropriate handler.

  if (MODEL_REGISTRY.imageGeneration.find(m => m.id === name)) {
    return await this.handleImageGeneration(args, model);
  } else if (MODEL_REGISTRY.textToVideo.find(m => m.id === name)) {
    return await this.handleTextToVideo(args, model);
  } else if (MODEL_REGISTRY.imageToVideo.find(m => m.id === name)) {
    return await this.handleImageToVideo(args, model);
  }